Skip to content

Latest commit

 

History

History
103 lines (78 loc) · 1.84 KB

README.md

File metadata and controls

103 lines (78 loc) · 1.84 KB
Raw

Table of Contents

About The Project

Solution for the mushroom-challenge

Getting Started

Get the code running.

Prerequisites

You need the following software

npm install angular -g

Installation

  1. Clone the repo
git clone https://github.com/JanKru/mushroomClassifier.git
  1. Navigate to mushroomClassifier/backend
cd ./mushroomClassifier/backend
  1. Create a .env-file (like the example below)
NODE_ENV=development
SERVER_PORT=4041
MONGO_HOST=mongodb://localhost/mushroomClassifier

JWT_SECRET=SECRET#1234
JWT_EXP=20m

HIDDEN_LAYERS=[200]
ITERATIONS=20000
ERRORTHRESH=0.005
LEARNING_RATE=0.3
TIMEOUT=120000

THRESHOLDTOBEPOISONOUS=85
  1. Install NPM packages
npm install
  1. If you want to run backend: unit test
npm test
  1. Navigate to the frontend diretory
cd ../mushroomClassifier/frontend
  1. Install NPM packages
npm install
  1. Start the frontend
ng serve --open
  1. Start the backend (backend dir)
node index.js
  1. Open Webpage and register a new user

Usage

Start the server (node index.js) and frontend (ng serve --open) Be sure mongoDB is running

When your work on Mac your linter may marks the linebreaks. Go to .eslintrc and change linebreak style to unix

 "linebreak-style": ["error", "unix"]

ToDo

  • solve the responsive problem in modal
  • Capsules the individual modules correctly
  • Write more tests, especially for the neural network. Possibly train with a smaller amount of data first and then test it